AI Threat Intelligence Detection Model

This project builds a backend AI-based model to classify network traffic as either benign or attack using supervised machine learning techniques. It processes CSV network flow data, trains a Random Forest model, and outputs a trained model for further use.

---

📂 Project Structure

File	Description
app.py	Complete code for data cleaning, preprocessing, model training, evaluation, and saving the trained model
cleaned_dataset.csv	Cleaned dataset used for model training
ai_threat_intelligence_model.pkl	Trained machine learning model
scaler.pkl	Trained scaler object used for feature scaling
.gitignore	Files/directories excluded from version control
requirements.txt	Required dependencies to run the project

---

📊 Dataset

The dataset used in this project is publicly available on Kaggle:

👉 IDS Intrusion CSV Dataset - Kaggle

File used: 02-14-2018.csv

After downloading, place 02-14-2018.csv inside the project root directory.

---

🚀 Workflow

1. Load and clean the dataset
2. Handle missing values and irrelevant columns
3. Perform label encoding
4. Conduct exploratory data analysis (EDA)
5. Train a Random Forest Classifier
6. Evaluate model performance
7. Save trained model and scaler

---

⚙ Technologies Used

• Python
• pandas
• numpy
• seaborn
• matplotlib
• scikit-learn
• joblib

---

💻 How to Run

1️⃣ Clone this repository

git clone https://github.com/yourusername/ai-threat-intelligence.git
cd ai-threat-intelligence